8 citations · 14 across the 4 of their papers we have counts for
4 papers
LAST: Scalable Lattice-Based Speech Modelling in JAX
Ke Wu, Ehsan Variani, Tom Bagby +1
We introduce LAST, a LAttice-based Speech Transducer library in JAX. With an emphasis on flexibility, ease-of-use, and scalability, LAST implements differentiable weighted finite s…
Alignment Entropy Regularization
Ehsan Variani, Ke Wu, David Rybach +2
Existing training criteria in automatic speech recognition(ASR) permit the model to freely explore more than one time alignments between the feature and label sequences. In this pa…
Global Normalization for Streaming Speech Recognition in a Modular Framework
Ehsan Variani, Ke Wu, Michael Riley +3
We introduce the Globally Normalized Autoregressive Transducer (GNAT) for addressing the label bias problem in streaming speech recognition. Our solution admits a tractable exact c…
Transformer-based Models of Text Normalization for Speech Applications
Jae Hun Ro, Felix Stahlberg, Ke Wu +1
Text normalization, or the process of transforming text into a consistent, canonical form, is crucial for speech applications such as text-to-speech synthesis (TTS). In TTS, the sy…